Qwen2-VL 2B
Qwen/Qwen2-VL-2B-Instruct
Parameters
2B
Context
32K
Downloads
2.5M
Likes
518
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 8.3 GB RAM 32.0 · Disk 44.8 | 10.7 GB RAM 32.0 · Disk 70.8 | 26.7 GB RAM 40.1 · Disk 109.8 |
| FP88bit | 5.9 GB RAM 32.0 · Disk 41.9 | 8.2 GB RAM 32.0 · Disk 67.9 | 24.2 GB RAM 36.3 · Disk 106.9 |
| INT88bit | 5.9 GB RAM 32.0 · Disk 41.9 | 8.2 GB RAM 32.0 · Disk 67.9 | 24.2 GB RAM 36.3 · Disk 106.9 |
| AWQ4bit | 4.8 GB RAM 32.0 · Disk 40.5 | 7.0 GB RAM 32.0 · Disk 66.5 | 22.9 GB RAM 34.4 · Disk 105.5 |
| GPTQ4bit | 4.8 GB RAM 32.0 · Disk 40.5 | 7.0 GB RAM 32.0 · Disk 66.5 | 23.0 GB RAM 34.4 · Disk 105.5 |
| GGUF4bit | 4.8 GB RAM 32.0 · Disk 40.6 | 7.1 GB RAM 32.0 · Disk 66.6 | 23.0 GB RAM 34.5 · Disk 105.6 |
GPU Recommendations
1× RTX 3080 Ti
12 GB VRAM
≈ 940.2 tok/s
Effective production throughput ≈ 658.1 tok/s
score 0.6511
1× RTX 3080
10 GB VRAM
≈ 783.5 tok/s
Effective production throughput ≈ 548.4 tok/s
score 0.6817
8× RTX 5090
256 GB VRAM
≈ 5911.8 tok/s
Effective production throughput ≈ 4138.3 tok/s
score 0.352
1× RTX 3090
24 GB VRAM
≈ 964.9 tok/s
Effective production throughput ≈ 675.4 tok/s
score 0.573
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 3080
10 GB VRAM
$58.6
/mo · vast
Tesla V100
16 GB VRAM
$66.7
/mo · vast
RTX 4060 Ti
8 GB VRAM
$78.4
/mo · vast
RTX 3080 Ti
12 GB VRAM
$79.5
/mo · vast
RTX 3090
24 GB VRAM
$88.4
/mo · vast